Automated Evaluation of Cardiac Function with Data-Driven Medical Ultrasound System

2022 Fiscal Year Final Research Report

• Project/Area Number: 18H04122
• Research Category: Grant-in-Aid for Scientific Research (A)
• Allocation Type: Single-year Grants
• Section: 一般
• Review Section: Medium-sized Section 62:Applied informatics and related fields
• Research Institution: The University of Tokyo
• Principal Investigator: Kotani Kiyoshi 東京大学, 先端科学技術研究センター, 准教授 (00372409)
• Co-Investigator(Kenkyū-buntansha): 武田 憲彦 自治医科大学, 医学部, 教授 (40422307) ; 仙波 宏章 東京大学, 医学部附属病院, 届出研究員 (80747923)
• Project Period (FY): 2018-04-01 – 2022-03-31
• Keywords: 医療用超音波検査

Outline of Final Research Achievements

In this study, we analyzed mouse echocardiograms and constructed a human echocardiographic acquisition system. In the analysis of mouse echocardiograms, the data-driven analysis using feature points in heart motion showed that the difference between the group treated with transverse aortic constriction and the control group appeared in the late systolic phase. Then we constructed an ultrasound image acquisition and analysis system for human echocardiography that is linked to the examinee's information and probe information. The system enables the echocardiographic probe to be guided to the appropriate position and posture.

Free Research Field

生体信号処理

Academic Significance and Societal Importance of the Research Achievements

マウス心エコー解析について，心臓の動きの特徴をデータ駆動的に解析する，心エコーに特化した説明可能な学習器を提案し構築した．この提案手法は心不全初期の特徴評価に有用であるため，今後の心エコー解析による心不全の理解に重要なものと考えられる．また，ロボットによる超音波取得についても今後の遠隔医療や個別医療の発展に向けて大きな社会的な意義がある成果と考えられる．